Discriminant analysis builds a predictive model for group membership. The model is composed of a discriminant function (or, for more than two groups, a set of discriminant functions) based on linear combinations of the predictor variables that provide the best discrimination between the groups. The functions are generated from a sample of cases for which group membership is known; the functions can then be applied to new cases that have measurements for the predictor variables but have unknown group membership.

Example. A telecommunications company can use discriminant analysis to classify customers into groups based on usage data. This allows them to score potential customers and target those who are most likely to be in the most valuable groups.

Requirements. You need one or more input fields and exactly one target field. The target must be a categorical field (with a measurement level of Flag or Nominal) with string or integer storage. (Storage can be converted using a Filler or Derive node if necessary. ) Fields set to Both or None are ignored. Fields used in the model must have their types fully instantiated.

Strengths. Discriminant analysis and Logistic Regression are both suitable classification models. However, Discriminant analysis makes more assumptions about the input fields—for example, they are normally distributed and should be continuous, and they give better results if those requirements are met, especially if the sample size is small.